Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5970 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5769. Min Range: -5.5769
Max Act: 5.5769. Min Act: -0.1700
Data Index: 8448626 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5769. Min Range: -5.5769
Max Act: 5.5769. Min Act: -0.1700
Data Index: 1353890 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5769. Min Range: -5.5769
Max Act: 5.5144. Min Act: -0.1700
Data Index: 5308602 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5769. Min Range: -5.5769
Max Act: 5.4832. Min Act: -0.1700
Data Index: 8626720 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5769. Min Range: -5.5769
Max Act: 5.5144. Min Act: -0.1700
Data Index: 232970 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5769. Min Range: -5.5769
Max Act: 5.4519. Min Act: -0.1700
Data Index: 3000137 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5769. Min Range: -5.5769
Max Act: 5.4519. Min Act: -0.1700
Data Index: 2394511 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5769. Min Range: -5.5769
Max Act: 5.4519. Min Act: -0.1700
Data Index: 4034206 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5769. Min Range: -5.5769
Max Act: 5.4207. Min Act: -0.1700
Data Index: 815885 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5769. Min Range: -5.5769
Max Act: 5.4207. Min Act: -0.1700
Data Index: 7579425 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5769. Min Range: -5.5769
Max Act: 5.4207. Min Act: -0.1700
Data Index: 4625911 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5769. Min Range: -5.5769
Max Act: 5.4207. Min Act: -0.1700
Data Index: 6332363 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5769. Min Range: -5.5769
Max Act: 5.4207. Min Act: -0.1700
Data Index: 5933967 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5769. Min Range: -5.5769
Max Act: 5.4207. Min Act: -0.1700
Data Index: 1112017 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5769. Min Range: -5.5769
Max Act: 5.3894. Min Act: -0.1700
Data Index: 5411047 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5769. Min Range: -5.5769
Max Act: 5.3894. Min Act: -0.1700
Data Index: 4050498 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5769. Min Range: -5.5769
Max Act: 5.3894. Min Act: -0.1700
Data Index: 232976 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5769. Min Range: -5.5769
Max Act: 5.3894. Min Act: -0.1700
Data Index: 5631891 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5769. Min Range: -5.5769
Max Act: 5.3894. Min Act: -0.1700
Data Index: 441958 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5769. Min Range: -5.5769
Max Act: 5.3894. Min Act: -0.1700
Data Index: 3783775 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19